Precipitation patterns from 1981-1989

library(tidyverse)

## Loading tidyverse: ggplot2
## Loading tidyverse: tibble
## Loading tidyverse: tidyr
## Loading tidyverse: readr
## Loading tidyverse: purrr
## Loading tidyverse: dplyr

## Conflicts with tidy packages ----------------------------------------------

## filter(): dplyr, stats
## lag():    dplyr, stats

library(janitor)
library(stringr)
library(forcats)
library(viridis)

## Loading required package: viridisLite

library(plotly)

## 
## Attaching package: 'plotly'

## The following object is masked from 'package:ggplot2':
## 
##     last_plot

## The following object is masked from 'package:stats':
## 
##     filter

## The following object is masked from 'package:graphics':
## 
##     layout

library(ggplot2)
library(ggthemes)

ny_noaa_data_tidy = read_csv("./nynoaadat.zip") %>%
  clean_names() %>%
  drop_na() %>%
  separate(date, into = c("year", "month", "day"), "-") %>%
  mutate(month = as.factor(month), prcp = as.numeric(prcp), tmin = as.numeric(tmin), 
         prcp = prcp / 10,
         tmin = tmin / 10) %>% 
  mutate(month = recode(month,
                          "01" = "January",
                          "02" = "February",
                          "03" = "March",
                          "04" = "April",
                          "05" = "May",
                          "06" = "June",
                          "07" = "July",
                          "08" = "August",
                          "09" = "September",
                          "10" = "October",
                          "11" = "November",
                          "12" = "December")) %>%
  select (year, month, day, prcp, tmin, snow) %>%
  filter(year <= "1989")

## Parsed with column specification:
## cols(
##   id = col_character(),
##   date = col_date(format = ""),
##   prcp = col_integer(),
##   snow = col_integer(),
##   snwd = col_integer(),
##   tmax = col_character(),
##   tmin = col_character()
## )

geom_path_ggplot = 
ny_noaa_data_tidy %>%
  group_by(month, year) %>%
  summarize(average_prcp = mean(prcp, na.rm = TRUE)) %>%
   ggplot(aes(x = month, y = average_prcp, group = year, color = year)) +
  geom_path(alpha = 0.4)+
  theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
  labs(x = "Month", y = "average precipitation (mm)")
    
ggplotly(geom_path_ggplot)

## We recommend that you use the dev version of ggplot2 with `ggplotly()`
## Install it with: `devtools::install_github('hadley/ggplot2')`

ny_noaa_data_tidy %>%
  group_by(year) %>%
   plot_ly(y = ~tmin, x = ~year, color = ~year, type = "box",
          colors = "Set2") 

geom_smooth_ggplot =
  ny_noaa_data_tidy %>% 
  ggplot(aes(x = tmin, y = prcp)) +
geom_smooth() +
 labs( x = "tmin", y = "prcp")

ggplotly(geom_smooth_ggplot)

## We recommend that you use the dev version of ggplot2 with `ggplotly()`
## Install it with: `devtools::install_github('hadley/ggplot2')`

## `geom_smooth()` using method = 'gam'